[LoopVectorize] Fix divide-by-zero bug (#80836)

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -2106,16 +2106,18 @@ class GeneratedRTChecks {
               BestTripCount = *EstimatedTC;
           }
 
+          BestTripCount = std::max(BestTripCount, 1U);
           InstructionCost NewMemCheckCost = MemCheckCost / BestTripCount;
 
           // Let's ensure the cost is always at least 1.
           NewMemCheckCost = std::max(*NewMemCheckCost.getValue(),
                                      (InstructionCost::CostType)1);
 
-          LLVM_DEBUG(dbgs()
-                     << "We expect runtime memory checks to be hoisted "
-                     << "out of the outer loop. Cost reduced from "
-                     << MemCheckCost << " to " << NewMemCheckCost << '\n');
+          if (BestTripCount > 1)
+            LLVM_DEBUG(dbgs()
+                       << "We expect runtime memory checks to be hoisted "
+                       << "out of the outer loop. Cost reduced from "
+                       << MemCheckCost << " to " << NewMemCheckCost << '\n');
 
           MemCheckCost = NewMemCheckCost;
         }

llvm/test/Transforms/LoopVectorize/AArch64/low_trip_memcheck_cost.ll

@@ -177,6 +177,43 @@ outer.exit:
 }
 
 
+define void @outer_pgo_minus1(ptr nocapture noundef %a, ptr nocapture noundef readonly %b, i64 noundef %m, i64 noundef %n) {
+; CHECK-LABEL: LV: Checking a loop in 'outer_pgo_minus1'
+; CHECK:      Calculating cost of runtime checks:
+; CHECK-NOT:  We expect runtime memory checks to be hoisted out of the outer loop. Cost reduced
+; CHECK:      Total cost of runtime checks: 6
+; CHECK-NEXT: LV: Minimum required TC for runtime checks to be profitable:16
+entry:
+  br label %outer.loop
+
+outer.loop:
+  %outer.iv = phi i64 [ %outer.iv.next, %inner.exit ], [ 0, %entry ]
+  %mul.us = mul nsw i64 %outer.iv, %n
+  br label %inner.loop
+
+inner.loop:
+  %inner.iv = phi i64 [ 0, %outer.loop ], [ %inner.iv.next, %inner.loop ]
+  %add.us = add nuw nsw i64 %inner.iv, %mul.us
+  %arrayidx.us = getelementptr inbounds i8, ptr %b, i64 %add.us
+  %0 = load i8, ptr %arrayidx.us, align 1
+  %arrayidx7.us = getelementptr inbounds i8, ptr %a, i64 %add.us
+  %1 = load i8, ptr %arrayidx7.us, align 1
+  %add9.us = add i8 %1, %0
+  store i8 %add9.us, ptr %arrayidx7.us, align 1
+  %inner.iv.next = add nuw nsw i64 %inner.iv, 1
+  %exitcond.not = icmp eq i64 %inner.iv.next, %n
+  br i1 %exitcond.not, label %inner.exit, label %inner.loop
+
+inner.exit:
+  %outer.iv.next = add nuw nsw i64 %outer.iv, 1
+  %exitcond26.not = icmp eq i64 %outer.iv.next, %m
+  br i1 %exitcond26.not, label %outer.exit, label %outer.loop, !prof !1
+
+outer.exit:
+  ret void
+}
+
+
 define void @outer_known_tc3_full_range_checks(ptr nocapture noundef %dst, ptr nocapture noundef readonly %src, i64 noundef %n) {
 ; CHECK-LABEL: LV: Checking a loop in 'outer_known_tc3_full_range_checks'
 ; CHECK:      Calculating cost of runtime checks:
@@ -215,3 +252,4 @@ outer.exit:
 
 
 !0 = !{!"branch_weights", i32 10, i32 20}
+!1 = !{!"branch_weights", i32 1, i32 -1}